© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29731
    Prev
    Next
    INDEX
    Explanations

    .orgREADME.md

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を有
    0.37
     بس
    0.35
     Purdue
    0.34
    ٥
    0.34
     CDR
    0.34
    魟
    0.34
    enas
    0.33
     تز
    0.33
    CDR
    0.33
     spis
    0.33
    POSITIVE LOGITS
    myLabels
    0.38
     Theoretical
    0.37
    娩
    0.37
     অনুম
    0.37
    landers
    0.37
     timeCounter
    0.37
     foco
    0.36
    standards
    0.35
    ्मण
    0.34
     econôm
    0.34
    Activations Density 0.014%

    No Known Activations